Adversarial Robustness on Image Classification with $k$-means

Abstract

In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks, emphasising the associated security risks. Our study investigates the impact of incremental attack strength on training, introduces the concept of transferability between supervised and unsupervised models, and highlights the sensitivity of unsupervised models to sample distributions. We additionally introduce and evaluate an adversarial training method that improves testing performance in adversarial scenarios, and we highlight the importance of various parameters in the proposed training method, such as continuous learning, centroid initialisation, and adversarial step-count.

arXiv comment6 pages, 3 figures, 2 equations, 1 algorithm

References in corpus (10)

• Explaining and Harnessing Adversarial Examples
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Intriguing properties of neural networks
• One pixel attack for fooling deep neural networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Evasion Attacks against Machine Learning at Test Time
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Certified Defenses against Adversarial Examples
• The Space of Transferable Adversarial Examples
• Image Super-Resolution as a Defense Against Adversarial Attacks